Research

Paper

TESTING March 17, 2026

SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment

Authors

Zhouwei Zhai, Mengxiang Chen, Anmeng Zhang

Abstract

Large language models offer transformative potential for e-commerce search by enabling intent-aware recommendations. However, their industrial deployment is hindered by two critical challenges: (1) knowledge hallucination due to insufficient encoding of dynamic, fine-grained product knowledge, and (2) security vulnerabilities under jailbreak attacks that threaten compliance. To address these issues, we propose SI--a Synthesize-Inject-Align framework for building knowledgeable and secure e-commerce search LLMs. Our approach first synthesizes high-quality natural language corpus by combining structured knowledge graphs with unstructured behavioral logs, augmented with reasoning chains and safety-aware data.We then introduce a parameter-efficient pre-training strategy based on Depth Up-Scaling to inject domain knowledge while preserving general capabilities. Finally, a dual-path alignment method via multi-task instruction tuning and adversarial training strengthens both task performance and safety robustness. The framework has been deployed at JD.com, China's largest self-operated e-commerce platform, where A/B tests across five core search scenarios demonstrate significant improvements in key business metrics, validating its industrial effectiveness and scalability.

Metadata

arXiv ID: 2603.16137
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16137v1</id>\n    <title>SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment</title>\n    <updated>2026-03-17T05:41:22Z</updated>\n    <link href='https://arxiv.org/abs/2603.16137v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16137v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large language models offer transformative potential for e-commerce search by enabling intent-aware recommendations. However, their industrial deployment is hindered by two critical challenges: (1) knowledge hallucination due to insufficient encoding of dynamic, fine-grained product knowledge, and (2) security vulnerabilities under jailbreak attacks that threaten compliance. To address these issues, we propose SI--a Synthesize-Inject-Align framework for building knowledgeable and secure e-commerce search LLMs. Our approach first synthesizes high-quality natural language corpus by combining structured knowledge graphs with unstructured behavioral logs, augmented with reasoning chains and safety-aware data.We then introduce a parameter-efficient pre-training strategy based on Depth Up-Scaling to inject domain knowledge while preserving general capabilities. Finally, a dual-path alignment method via multi-task instruction tuning and adversarial training strengthens both task performance and safety robustness. The framework has been deployed at JD.com, China's largest self-operated e-commerce platform, where A/B tests across five core search scenarios demonstrate significant improvements in key business metrics, validating its industrial effectiveness and scalability.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-17T05:41:22Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Zhouwei Zhai</name>\n    </author>\n    <author>\n      <name>Mengxiang Chen</name>\n    </author>\n    <author>\n      <name>Anmeng Zhang</name>\n    </author>\n  </entry>"
}